String 概述
String 是Java 语言中的常用类，用来保存常量字符串，不可改变。
接口实现
String 实现了 java.io.Serializable, Comparable, CharSequence 3个接口。
字符存储方式
/** The value is used for character storage. */
private final char value[];
String 通过定义一个字符数组保存字符串。
构造函数
/**
* Initializes a newly created {@code String} object so that it represents
* an empty character sequence. Note that use of this constructor is
* unnecessary since Strings are immutable.
*/
public String() {
this.value = "".value;
}
/**
* Initializes a newly created {@code String} object so that it represents
* the same sequence of characters as the argument; in other words, the
* newly created string is a copy of the argument string. Unless an
* explicit copy of {@code original} is needed, use of this constructor is
* unnecessary since Strings are immutable.
*
* @param original
* A {@code String}
*/
public String(String original) {
this.value = original.value;
this.hash = original.hash;
}
/**
* Allocates a new {@code String} so that it represents the sequence of
* characters currently contained in the character array argument. The
* contents of the character array are copied; subsequent modification of
* the character array does not affect the newly created string.
*
* @param value
* The initial value of the string
*/
public String(char value[]) {
this.value = Arrays.copyOf(value, value.length);
}
/**
* Allocates a new {@code String} that contains characters from a subarray
* of the character array argument. The {@code offset} argument is the
* index of the first character of the subarray and the {@code count}
* argument specifies the length of the subarray. The contents of the
* subarray are copied; subsequent modification of the character array does
* not affect the newly created string.
*
* @param value
* Array that is the source of characters
*
* @param offset
* The initial offset
*
* @param count
* The length
*
* @throws IndexOutOfBoundsException
* If the {@code offset} and {@code count} arguments index
* characters outside the bounds of the {@code value} array
*/
public String(char value[], int offset, int count) {
if (offset < 0) {
throw new StringIndexOutOfBoundsException(offset);
}
if (count <= 0) {
if (count < 0) {
throw new StringIndexOutOfBoundsException(count);
}
if (offset <= value.length) {
this.value = "".value;
return;
}
}
// Note: offset or count might be near -1>>>1.
if (offset > value.length - count) {
throw new StringIndexOutOfBoundsException(offset + count);
}
this.value = Arrays.copyOfRange(value, offset, offset+count);
}
4个构造函数比较简单，不多做解释。
方法实现
基础防范：字符串长度，是否为空，指定位置字符
/**
* Returns the length of this string.
* The length is equal to the number of <a href="Character.html#unicode">Unicode
* code units</a> in the string.
*
* @return the length of the sequence of characters represented by this
* object.
*/
public int length() {
return value.length;
}
/**
* Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
*
* @return {@code true} if {@link #length()} is {@code 0}, otherwise
* {@code false}
*
* @since 1.6
*/
public boolean isEmpty() {
return value.length == 0;
}
/**
* Returns the {@code char} value at the
* specified index. An index ranges from {@code 0} to
* {@code length() - 1}. The first {@code char} value of the sequence
* is at index {@code 0}, the next at index {@code 1},
* and so on, as for array indexing.
*
* <p>If the {@code char} value specified by the index is a
* <a href="Character.html#unicode">surrogate</a>, the surrogate
* value is returned.
*
* @param index the index of the {@code char} value.
* @return the {@code char} value at the specified index of this string.
* The first {@code char} value is at index {@code 0}.
* @exception IndexOutOfBoundsException if the {@code index}
* argument is negative or not less than the length of this
* string.
*/
public char charAt(int index) {
if ((index < 0) || (index >= value.length)) {
throw new StringIndexOutOfBoundsException(index);
}
return value[index];
}
字符串对比
/**
* Compares this string to the specified object. The result is {@code
* true} if and only if the argument is not {@code null} and is a {@code
* String} object that represents the same sequence of characters as this
* object.
*
* @param anObject
* The object to compare this {@code String} against
*
* @return {@code true} if the given object represents a {@code String}
* equivalent to this string, {@code false} otherwise
*
* @see #compareTo(String)
* @see #equalsIgnoreCase(String)
*/
public boolean equals(Object anObject) {
if (this == anObject) {
return true;
}
if (anObject instanceof String) {
String anotherString = (String)anObject;
int n = value.length;
if (n == anotherString.value.length) {
char v1[] = value;
char v2[] = anotherString.value;
int i = 0;
while (n-- != 0) {
if (v1[i] != v2[i])
return false;
i++;
}
return true;
}
}
return false;
}
/**
* Compares this string to the specified {@code StringBuffer}. The result
* is {@code true} if and only if this {@code String} represents the same
* sequence of characters as the specified {@code StringBuffer}. This method
* synchronizes on the {@code StringBuffer}.
*
* @param sb
* The {@code StringBuffer} to compare this {@code String} against
*
* @return {@code true} if this {@code String} represents the same
* sequence of characters as the specified {@code StringBuffer},
* {@code false} otherwise
*
* @since 1.4
*/
public boolean contentEquals(StringBuffer sb) {
return contentEquals((CharSequence)sb);
}
private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
char v1[] = value;
char v2[] = sb.getValue();
int n = v1.length;
if (n != sb.length()) {
return false;
}
for (int i = 0; i < n; i++) {
if (v1[i] != v2[i]) {
return false;
}
}
return true;
}
/**
* Compares this string to the specified {@code CharSequence}. The
* result is {@code true} if and only if this {@code String} represents the
* same sequence of char values as the specified sequence. Note that if the
* {@code CharSequence} is a {@code StringBuffer} then the method
* synchronizes on it.
*
* @param cs
* The sequence to compare this {@code String} against
*
* @return {@code true} if this {@code String} represents the same
* sequence of char values as the specified sequence, {@code
* false} otherwise
*
* @since 1.5
*/
public boolean contentEquals(CharSequence cs) {
// Argument is a StringBuffer, StringBuilder
if (cs instanceof AbstractStringBuilder) {
if (cs instanceof StringBuffer) {
synchronized(cs) {
return nonSyncContentEquals((AbstractStringBuilder)cs);
}
} else {
return nonSyncContentEquals((AbstractStringBuilder)cs);
}
}
// Argument is a String
if (cs instanceof String) {
return equals(cs);
}
// Argument is a generic CharSequence
char v1[] = value;
int n = v1.length;
if (n != cs.length()) {
return false;
}
for (int i = 0; i < n; i++) {
if (v1[i] != cs.charAt(i)) {
return false;
}
}
return true;
}
/**
* Compares this {@code String} to another {@code String}, ignoring case
* considerations. Two strings are considered equal ignoring case if they
* are of the same length and corresponding characters in the two strings
* are equal ignoring case.
*
* <p> Two characters {@code c1} and {@code c2} are considered the same
* ignoring case if at least one of the following is true:
* <ul>
* <li> The two characters are the same (as compared by the
* {@code ==} operator)
* <li> Applying the method {@link
* java.lang.Character#toUpperCase(char)} to each character
* produces the same result
* <li> Applying the method {@link
* java.lang.Character#toLowerCase(char)} to each character
* produces the same result
* </ul>
*
* @param anotherString
* The {@code String} to compare this {@code String} against
*
* @return {@code true} if the argument is not {@code null} and it
* represents an equivalent {@code String} ignoring case; {@code
* false} otherwise
*
* @see #equals(Object)
*/
public boolean equalsIgnoreCase(String anotherString) {
return (this == anotherString) ? true
: (anotherString != null)
&& (anotherString.value.length == value.length)
&& regionMatches(true, 0, anotherString, 0, value.length);
}
/**
* Compares two strings lexicographically.
* The comparison is based on the Unicode value of each character in
* the strings. The character sequence represented by this
* {@code String} object is compared lexicographically to the
* character sequence represented by the argument string. The result is
* a negative integer if this {@code String} object
* lexicographically precedes the argument string. The result is a
* positive integer if this {@code String} object lexicographically
* follows the argument string. The result is zero if the strings
* are equal; {@code compareTo} returns {@code 0} exactly when
* the {@link #equals(Object)} method would return {@code true}.
* <p>
* This is the definition of lexicographic ordering. If two strings are
* different, then either they have different characters at some index
* that is a valid index for both strings, or their lengths are different,
* or both. If they have different characters at one or more index
* positions, let <i>k</i> be the smallest such index; then the string
* whose character at position <i>k</i> has the smaller value, as
* determined by using the < operator, lexicographically precedes the
* other string. In this case, {@code compareTo} returns the
* difference of the two character values at position {@code k} in
* the two string -- that is, the value:
* <blockquote><pre>
* this.charAt(k)-anotherString.charAt(k)
* </pre></blockquote>
* If there is no index position at which they differ, then the shorter
* string lexicographically precedes the longer string. In this case,
* {@code compareTo} returns the difference of the lengths of the
* strings -- that is, the value:
* <blockquote><pre>
* this.length()-anotherString.length()
* </pre></blockquote>
*
* @param anotherString the {@code String} to be compared.
* @return the value {@code 0} if the argument string is equal to
* this string; a value less than {@code 0} if this string
* is lexicographically less than the string argument; and a
* value greater than {@code 0} if this string is
* lexicographically greater than the string argument.
*/
public int compareTo(String anotherString) {
int len1 = value.length;
int len2 = anotherString.value.length;
int lim = Math.min(len1, len2);
char v1[] = value;
char v2[] = anotherString.value;
int k = 0;
while (k < lim) {
char c1 = v1[k];
char c2 = v2[k];
if (c1 != c2) {
return c1 - c2;
}
k++;
}
return len1 - len2;
}
/**
* A Comparator that orders {@code String} objects as by
* {@code compareToIgnoreCase}. This comparator is serializable.
* <p>
* Note that this Comparator does <em>not</em> take locale into account,
* and will result in an unsatisfactory ordering for certain locales.
* The java.text package provides <em>Collators</em> to allow
* locale-sensitive ordering.
*
* @see java.text.Collator#compare(String, String)
* @since 1.2
*/
public static final Comparator<String> CASE_INSENSITIVE_ORDER
= new CaseInsensitiveComparator();
private static class CaseInsensitiveComparator
implements Comparator<String>, java.io.Serializable {
// use serialVersionUID from JDK 1.2.2 for interoperability
private static final long serialVersionUID = 8575799808933029326L;
public int compare(String s1, String s2) {
int n1 = s1.length();
int n2 = s2.length();
int min = Math.min(n1, n2);
for (int i = 0; i < min; i++) {
char c1 = s1.charAt(i);
char c2 = s2.charAt(i);
if (c1 != c2) {
c1 = Character.toUpperCase(c1);
c2 = Character.toUpperCase(c2);
if (c1 != c2) {
c1 = Character.toLowerCase(c1);
c2 = Character.toLowerCase(c2);
if (c1 != c2) {
// No overflow because of numeric promotion
return c1 - c2;
}
}
}
}
return n1 - n2;
}
/** Replaces the de-serialized object. */
private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
}
/**
* Compares two strings lexicographically, ignoring case
* differences. This method returns an integer whose sign is that of
* calling {@code compareTo} with normalized versions of the strings
* where case differences have been eliminated by calling
* {@code Character.toLowerCase(Character.toUpperCase(character))} on
* each character.
* <p>
* Note that this method does <em>not</em> take locale into account,
* and will result in an unsatisfactory ordering for certain locales.
* The java.text package provides <em>collators</em> to allow
* locale-sensitive ordering.
*
* @param str the {@code String} to be compared.
* @return a negative integer, zero, or a positive integer as the
* specified String is greater than, equal to, or less
* than this String, ignoring case considerations.
* @see java.text.Collator#compare(String, String)
* @since 1.2
*/
public int compareToIgnoreCase(String str) {
return CASE_INSENSITIVE_ORDER.compare(this, str);
}
从代码可以看出，对比大小时，会考虑到字符串长度和对应位置字符比较。忽略大小写比较时，会将字符串同时转换成大小写进行比较，只要有一个相等即相等。
开头结尾匹配
/**
* Tests if the substring of this string beginning at the
* specified index starts with the specified prefix.
*
* @param prefix the prefix.
* @param toffset where to begin looking in this string.
* @return {@code true} if the character sequence represented by the
* argument is a prefix of the substring of this object starting
* at index {@code toffset}; {@code false} otherwise.
* The result is {@code false} if {@code toffset} is
* negative or greater than the length of this
* {@code String} object; otherwise the result is the same
* as the result of the expression
* <pre>
* this.substring(toffset).startsWith(prefix)
* </pre>
*/
public boolean startsWith(String prefix, int toffset) {
char ta[] = value;
int to = toffset;
char pa[] = prefix.value;
int po = 0;
int pc = prefix.value.length;
// Note: toffset might be near -1>>>1.
if ((toffset < 0) || (toffset > value.length - pc)) {
return false;
}
while (--pc >= 0) {
if (ta[to++] != pa[po++]) {
return false;
}
}
return true;
}
/**
* Tests if this string starts with the specified prefix.
*
* @param prefix the prefix.
* @return {@code true} if the character sequence represented by the
* argument is a prefix of the character sequence represented by
* this string; {@code false} otherwise.
* Note also that {@code true} will be returned if the
* argument is an empty string or is equal to this
* {@code String} object as determined by the
* {@link #equals(Object)} method.
* @since 1. 0
*/
public boolean startsWith(String prefix) {
return startsWith(prefix, 0);
}
/**
* Tests if this string ends with the specified suffix.
*
* @param suffix the suffix.
* @return {@code true} if the character sequence represented by the
* argument is a suffix of the character sequence represented by
* this object; {@code false} otherwise. Note that the
* result will be {@code true} if the argument is the
* empty string or is equal to this {@code String} object
* as determined by the {@link #equals(Object)} method.
*/
public boolean endsWith(String suffix) {
return startsWith(suffix, value.length - suffix.value.length);
}
startsWith和endsWith都是以指定位置开始比较字符串的基础方法实现。
指定位置字符
/**
* Returns the index within this string of the first occurrence of
* the specified character. If a character with value
* {@code ch} occurs in the character sequence represented by
* this {@code String} object, then the index (in Unicode
* code units) of the first such occurrence is returned. For
* values of {@code ch} in the range from 0 to 0xFFFF
* (inclusive), this is the smallest value <i>k</i> such that:
* <blockquote><pre>
* this.charAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* smallest value <i>k</i> such that:
* <blockquote><pre>
* this.codePointAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string, then {@code -1} is returned.
*
* @param ch a character (Unicode code point).
* @return the index of the first occurrence of the character in the
* character sequence represented by this object, or
* {@code -1} if the character does not occur.
*/
public int indexOf(int ch) {
return indexOf(ch, 0);
}
/**
* Returns the index within this string of the first occurrence of the
* specified character, starting the search at the specified index.
* <p>
* If a character with value {@code ch} occurs in the
* character sequence represented by this {@code String}
* object at an index no smaller than {@code fromIndex}, then
* the index of the first such occurrence is returned. For values
* of {@code ch} in the range from 0 to 0xFFFF (inclusive),
* this is the smallest value <i>k</i> such that:
* <blockquote><pre>
* (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* smallest value <i>k</i> such that:
* <blockquote><pre>
* (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string at or after position {@code fromIndex}, then
* {@code -1} is returned.
*
* <p>
* There is no restriction on the value of {@code fromIndex}. If it
* is negative, it has the same effect as if it were zero: this entire
* string may be searched. If it is greater than the length of this
* string, it has the same effect as if it were equal to the length of
* this string: {@code -1} is returned.
*
* <p>All indices are specified in {@code char} values
* (Unicode code units).
*
* @param ch a character (Unicode code point).
* @param fromIndex the index to start the search from.
* @return the index of the first occurrence of the character in the
* character sequence represented by this object that is greater
* than or equal to {@code fromIndex}, or {@code -1}
* if the character does not occur.
*/
public int indexOf(int ch, int fromIndex) {
final int max = value.length;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= max) {
// Note: fromIndex might be near -1>>>1.
return -1;
}
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
// handle most cases here (ch is a BMP code point or a
// negative value (invalid code point))
final char[] value = this.value;
for (int i = fromIndex; i < max; i++) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return indexOfSupplementary(ch, fromIndex);
}
}
/**
* Returns the index within this string of the last occurrence of
* the specified character. For values of {@code ch} in the
* range from 0 to 0xFFFF (inclusive), the index (in Unicode code
* units) returned is the largest value <i>k</i> such that:
* <blockquote><pre>
* this.charAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* largest value <i>k</i> such that:
* <blockquote><pre>
* this.codePointAt(<i>k</i>) == ch
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string, then {@code -1} is returned. The
* {@code String} is searched backwards starting at the last
* character.
*
* @param ch a character (Unicode code point).
* @return the index of the last occurrence of the character in the
* character sequence represented by this object, or
* {@code -1} if the character does not occur.
*/
public int lastIndexOf(int ch) {
return lastIndexOf(ch, value.length - 1);
}
/**
* Returns the index within this string of the last occurrence of
* the specified character, searching backward starting at the
* specified index. For values of {@code ch} in the range
* from 0 to 0xFFFF (inclusive), the index returned is the largest
* value <i>k</i> such that:
* <blockquote><pre>
* (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* largest value <i>k</i> such that:
* <blockquote><pre>
* (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string at or before position {@code fromIndex}, then
* {@code -1} is returned.
*
* <p>All indices are specified in {@code char} values
* (Unicode code units).
*
* @param ch a character (Unicode code point).
* @param fromIndex the index to start the search from. There is no
* restriction on the value of {@code fromIndex}. If it is
* greater than or equal to the length of this string, it has
* the same effect as if it were equal to one less than the
* length of this string: this entire string may be searched.
* If it is negative, it has the same effect as if it were -1:
* -1 is returned.
* @return the index of the last occurrence of the character in the
* character sequence represented by this object that is less
* than or equal to {@code fromIndex}, or {@code -1}
* if the character does not occur before that point.
*/
public int lastIndexOf(int ch, int fromIndex) {
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
// handle most cases here (ch is a BMP code point or a
// negative value (invalid code point))
final char[] value = this.value;
int i = Math.min(fromIndex, value.length - 1);
for (; i >= 0; i--) {
if (value[i] == ch) {
return i;
}
}
return -1;
} else {
return lastIndexOfSupplementary(ch, fromIndex);
}
}
如代码所示。
子串
/**
* Returns a string that is a substring of this string. The
* substring begins with the character at the specified index and
* extends to the end of this string. <p>
* Examples:
* <blockquote><pre>
* "unhappy".substring(2) returns "happy"
* "Harbison".substring(3) returns "bison"
* "emptiness".substring(9) returns "" (an empty string)
* </pre></blockquote>
*
* @param beginIndex the beginning index, inclusive.
* @return the specified substring.
* @exception IndexOutOfBoundsException if
* {@code beginIndex} is negative or larger than the
* length of this {@code String} object.
*/
public String substring(int beginIndex) {
if (beginIndex < 0) {
throw new StringIndexOutOfBoundsException(beginIndex);
}
int subLen = value.length - beginIndex;
if (subLen < 0) {
throw new StringIndexOutOfBoundsException(subLen);
}
return (beginIndex == 0) ? this : new String(value, beginIndex, subLen);
}
/**
* Returns a string that is a substring of this string. The
* substring begins at the specified {@code beginIndex} and
* extends to the character at index {@code endIndex - 1}.
* Thus the length of the substring is {@code endIndex-beginIndex}.
* <p>
* Examples:
* <blockquote><pre>
* "hamburger".substring(4, 8) returns "urge"
* "smiles".substring(1, 5) returns "mile"
* </pre></blockquote>
*
* @param beginIndex the beginning index, inclusive.
* @param endIndex the ending index, exclusive.
* @return the specified substring.
* @exception IndexOutOfBoundsException if the
* {@code beginIndex} is negative, or
* {@code endIndex} is larger than the length of
* this {@code String} object, or
* {@code beginIndex} is larger than
* {@code endIndex}.
*/
public String substring(int beginIndex, int endIndex) {
if (beginIndex < 0) {
throw new StringIndexOutOfBoundsException(beginIndex);
}
if (endIndex > value.length) {
throw new StringIndexOutOfBoundsException(endIndex);
}
int subLen = endIndex - beginIndex;
if (subLen < 0) {
throw new StringIndexOutOfBoundsException(subLen);
}
return ((beginIndex == 0) && (endIndex == value.length)) ? this
: new String(value, beginIndex, subLen);
}
/**
* Returns a character sequence that is a subsequence of this sequence.
*
* <p> An invocation of this method of the form
*
* <blockquote><pre>
* str.subSequence(begin, end)</pre></blockquote>
*
* behaves in exactly the same way as the invocation
*
* <blockquote><pre>
* str.substring(begin, end)</pre></blockquote>
*
* @apiNote
* This method is defined so that the {@code String} class can implement
* the {@link CharSequence} interface.
*
* @param beginIndex the begin index, inclusive.
* @param endIndex the end index, exclusive.
* @return the specified subsequence.
*
* @throws IndexOutOfBoundsException
* if {@code beginIndex} or {@code endIndex} is negative,
* if {@code endIndex} is greater than {@code length()},
* or if {@code beginIndex} is greater than {@code endIndex}
*
* @since 1.4
* @spec JSR-51
*/
public CharSequence subSequence(int beginIndex, int endIndex) {
return this.substring(beginIndex, endIndex);
}
字符串替换和分割
/**
* Replaces the first substring of this string that matches the given <a
* href="../util/regex/Pattern.html#sum">regular expression</a> with the
* given replacement.
*
* <p> An invocation of this method of the form
* <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
* yields exactly the same result as the expression
*
* <blockquote>
* <code>
* {@link java.util.regex.Pattern}.{@link
* java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
* java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
* java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
* </code>
* </blockquote>
*
*<p>
* Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
* replacement string may cause the results to be different than if it were
* being treated as a literal replacement string; see
* {@link java.util.regex.Matcher#replaceFirst}.
* Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
* meaning of these characters, if desired.
*
* @param regex
* the regular expression to which this string is to be matched
* @param replacement
* the string to be substituted for the first match
*
* @return The resulting {@code String}
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String replaceFirst(String regex, String replacement) {
return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
}
/**
* Replaces each substring of this string that matches the given <a
* href="../util/regex/Pattern.html#sum">regular expression</a> with the
* given replacement.
*
* <p> An invocation of this method of the form
* <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
* yields exactly the same result as the expression
*
* <blockquote>
* <code>
* {@link java.util.regex.Pattern}.{@link
* java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
* java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
* java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
* </code>
* </blockquote>
*
*<p>
* Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
* replacement string may cause the results to be different than if it were
* being treated as a literal replacement string; see
* {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
* Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
* meaning of these characters, if desired.
*
* @param regex
* the regular expression to which this string is to be matched
* @param replacement
* the string to be substituted for each match
*
* @return The resulting {@code String}
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String replaceAll(String regex, String replacement) {
return Pattern.compile(regex).matcher(this).replaceAll(replacement);
}
/**
* Replaces each substring of this string that matches the literal target
* sequence with the specified literal replacement sequence. The
* replacement proceeds from the beginning of the string to the end, for
* example, replacing "aa" with "b" in the string "aaa" will result in
* "ba" rather than "ab".
*
* @param target The sequence of char values to be replaced
* @param replacement The replacement sequence of char values
* @return The resulting string
* @since 1.5
*/
public String replace(CharSequence target, CharSequence replacement) {
return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
}
/**
* Splits this string around matches of the given
* <a href="../util/regex/Pattern.html#sum">regular expression</a>.
*
* <p> The array returned by this method contains each substring of this
* string that is terminated by another substring that matches the given
* expression or is terminated by the end of the string. The substrings in
* the array are in the order in which they occur in this string. If the
* expression does not match any part of the input then the resulting array
* has just one element, namely this string.
*
* <p> When there is a positive-width match at the beginning of this
* string then an empty leading substring is included at the beginning
* of the resulting array. A zero-width match at the beginning however
* never produces such empty leading substring.
*
* <p> The {@code limit} parameter controls the number of times the
* pattern is applied and therefore affects the length of the resulting
* array. If the limit <i>n</i> is greater than zero then the pattern
* will be applied at most <i>n</i> - 1 times, the array's
* length will be no greater than <i>n</i>, and the array's last entry
* will contain all input beyond the last matched delimiter. If <i>n</i>
* is non-positive then the pattern will be applied as many times as
* possible and the array can have any length. If <i>n</i> is zero then
* the pattern will be applied as many times as possible, the array can
* have any length, and trailing empty strings will be discarded.
*
* <p> The string {@code "boo:and:foo"}, for example, yields the
* following results with these parameters:
*
* <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
* <tr>
* <th>Regex</th>
* <th>Limit</th>
* <th>Result</th>
* </tr>
* <tr><td align=center>:</td>
* <td align=center>2</td>
* <td>{@code { "boo", "and:foo" }}</td></tr>
* <tr><td align=center>:</td>
* <td align=center>5</td>
* <td>{@code { "boo", "and", "foo" }}</td></tr>
* <tr><td align=center>:</td>
* <td align=center>-2</td>
* <td>{@code { "boo", "and", "foo" }}</td></tr>
* <tr><td align=center>o</td>
* <td align=center>5</td>
* <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
* <tr><td align=center>o</td>
* <td align=center>-2</td>
* <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
* <tr><td align=center>o</td>
* <td align=center>0</td>
* <td>{@code { "b", "", ":and:f" }}</td></tr>
* </table></blockquote>
*
* <p> An invocation of this method of the form
* <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
* yields the same result as the expression
*
* <blockquote>
* <code>
* {@link java.util.regex.Pattern}.{@link
* java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
* java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
* </code>
* </blockquote>
*
*
* @param regex
* the delimiting regular expression
*
* @param limit
* the result threshold, as described above
*
* @return the array of strings computed by splitting this string
* around matches of the given regular expression
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String[] split(String regex, int limit) {
/* fastpath if the regex is a
(1)one-char String and this character is not one of the
RegEx's meta characters ".$|()[{^?*+\\", or
(2)two-char String and the first char is the backslash and
the second is not the ascii digit or ascii letter.
*/
char ch = 0;
if (((regex.value.length == 1 &&
".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
(regex.length() == 2 &&
regex.charAt(0) == '\\' &&
(((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
((ch-'a')|('z'-ch)) < 0 &&
((ch-'A')|('Z'-ch)) < 0)) &&
(ch < Character.MIN_HIGH_SURROGATE ||
ch > Character.MAX_LOW_SURROGATE))
{
int off = 0;
int next = 0;
boolean limited = limit > 0;
ArrayList<String> list = new ArrayList<>();
while ((next = indexOf(ch, off)) != -1) {
if (!limited || list.size() < limit - 1) {
list.add(substring(off, next));
off = next + 1;
} else { // last one
//assert (list.size() == limit - 1);
list.add(substring(off, value.length));
off = value.length;
break;
}
}
// If no match was found, return this
if (off == 0)
return new String[]{this};
// Add remaining segment
if (!limited || list.size() < limit)
list.add(substring(off, value.length));
// Construct result
int resultSize = list.size();
if (limit == 0) {
while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
resultSize--;
}
}
String[] result = new String[resultSize];
return list.subList(0, resultSize).toArray(result);
}
return Pattern.compile(regex).split(this, limit);
}
/**
* Splits this string around matches of the given <a
* href="../util/regex/Pattern.html#sum">regular expression</a>.
*
* <p> This method works as if by invoking the two-argument {@link
* #split(String, int) split} method with the given expression and a limit
* argument of zero. Trailing empty strings are therefore not included in
* the resulting array.
*
* <p> The string {@code "boo:and:foo"}, for example, yields the following
* results with these expressions:
*
* <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
* <tr>
* <th>Regex</th>
* <th>Result</th>
* </tr>
* <tr><td align=center>:</td>
* <td>{@code { "boo", "and", "foo" }}</td></tr>
* <tr><td align=center>o</td>
* <td>{@code { "b", "", ":and:f" }}</td></tr>
* </table></blockquote>
*
*
* @param regex
* the delimiting regular expression
*
* @return the array of strings computed by splitting this string
* around matches of the given regular expression
*
* @throws PatternSyntaxException
* if the regular expression's syntax is invalid
*
* @see java.util.regex.Pattern
*
* @since 1.4
* @spec JSR-51
*/
public String[] split(String regex) {
return split(regex, 0);
}
基于正则表达式实现。
其他类型数据转换成字符串
/**
* Returns the string representation of the {@code Object} argument.
*
* @param obj an {@code Object}.
* @return if the argument is {@code null}, then a string equal to
* {@code "null"}; otherwise, the value of
* {@code obj.toString()} is returned.
* @see java.lang.Object#toString()
*/
public static String valueOf(Object obj) {
return (obj == null) ? "null" : obj.toString();
}
/**
* Returns the string representation of the {@code char} array
* argument. The contents of the character array are copied; subsequent
* modification of the character array does not affect the returned
* string.
*
* @param data the character array.
* @return a {@code String} that contains the characters of the
* character array.
*/
public static String valueOf(char data[]) {
return new String(data);
}
/**
* Returns the string representation of a specific subarray of the
* {@code char} array argument.
* <p>
* The {@code offset} argument is the index of the first
* character of the subarray. The {@code count} argument
* specifies the length of the subarray. The contents of the subarray
* are copied; subsequent modification of the character array does not
* affect the returned string.
*
* @param data the character array.
* @param offset initial offset of the subarray.
* @param count length of the subarray.
* @return a {@code String} that contains the characters of the
* specified subarray of the character array.
* @exception IndexOutOfBoundsException if {@code offset} is
* negative, or {@code count} is negative, or
* {@code offset+count} is larger than
* {@code data.length}.
*/
public static String valueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
/**
* Equivalent to {@link #valueOf(char[], int, int)}.
*
* @param data the character array.
* @param offset initial offset of the subarray.
* @param count length of the subarray.
* @return a {@code String} that contains the characters of the
* specified subarray of the character array.
* @exception IndexOutOfBoundsException if {@code offset} is
* negative, or {@code count} is negative, or
* {@code offset+count} is larger than
* {@code data.length}.
*/
public static String copyValueOf(char data[], int offset, int count) {
return new String(data, offset, count);
}
/**
* Equivalent to {@link #valueOf(char[])}.
*
* @param data the character array.
* @return a {@code String} that contains the characters of the
* character array.
*/
public static String copyValueOf(char data[]) {
return new String(data);
}
/**
* Returns the string representation of the {@code boolean} argument.
*
* @param b a {@code boolean}.
* @return if the argument is {@code true}, a string equal to
* {@code "true"} is returned; otherwise, a string equal to
* {@code "false"} is returned.
*/
public static String valueOf(boolean b) {
return b ? "true" : "false";
}
/**
* Returns the string representation of the {@code char}
* argument.
*
* @param c a {@code char}.
* @return a string of length {@code 1} containing
* as its single character the argument {@code c}.
*/
public static String valueOf(char c) {
char data[] = {c};
return new String(data, true);
}
/**
* Returns the string representation of the {@code int} argument.
* <p>
* The representation is exactly the one returned by the
* {@code Integer.toString} method of one argument.
*
* @param i an {@code int}.
* @return a string representation of the {@code int} argument.
* @see java.lang.Integer#toString(int, int)
*/
public static String valueOf(int i) {
return Integer.toString(i);
}
/**
* Returns the string representation of the {@code long} argument.
* <p>
* The representation is exactly the one returned by the
* {@code Long.toString} method of one argument.
*
* @param l a {@code long}.
* @return a string representation of the {@code long} argument.
* @see java.lang.Long#toString(long)
*/
public static String valueOf(long l) {
return Long.toString(l);
}
/**
* Returns the string representation of the {@code float} argument.
* <p>
* The representation is exactly the one returned by the
* {@code Float.toString} method of one argument.
*
* @param f a {@code float}.
* @return a string representation of the {@code float} argument.
* @see java.lang.Float#toString(float)
*/
public static String valueOf(float f) {
return Float.toString(f);
}
/**
* Returns the string representation of the {@code double} argument.
* <p>
* The representation is exactly the one returned by the
* {@code Double.toString} method of one argument.
*
* @param d a {@code double}.
* @return a string representation of the {@code double} argument.
* @see java.lang.Double#toString(double)
*/
public static String valueOf(double d) {
return Double.toString(d);
}
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
